ninjahawk/livenerf

Benchmark for tracking model capability after release.

Language modelsPython

3.2 Early signal Magnitude out of 10 — how fast interest is growing, not a quality score. Star growth looks organic. Data as of September 28, 2026, 02:55 UTC.

Open on Seismograph Open on GitHub

About the project

A benchmark for tracking whether a frontier model quietly degrades after release: it runs a frozen question panel daily and statistically measures drift in accuracy and token counts against the launch-week baseline.

Useful for

Run the daily question panel through headless Claude Code to collect a baseline
Check whether model accuracy dropped over a 10-day window after release
Track falling output token counts as an early sign of reduced model effort

README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.

Why it’s trending

0 stars so far today, about 30 expected by the end of the day.
The spike has held for 3 days in a row — not a one-off blip.
The repository is 6 days old and already has 84 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
Top new repositories this week: #157.

Stars per day

Bars are daily stars, the line is the usual pace. Red marks spike days.

Numbers

Total stars: 84
Today: 0 · ≈ 30 by evening
Forks: 4
Issues and pull requests: 5
Watchers: 5
Language: Python
Created: September 22, 2026
Last push: September 27, 2026

Star trust

Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.

These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.

Spotted in

September 28, 2026Top new repositories this week: #157

README badge

Paste it into your README — the badge shows the current magnitude and links to this page.

[![Seismograph](https://gitnova.dev/badge/ninjahawk/livenerf.svg?lang=en)](https://gitnova.dev/en/r/ninjahawk/livenerf)

More in this category

6.9
Niko1221/Strata
A C++ local inference engine that runs the 125B MoE model Qwen3.8-Flash-Next on a regular PC with one NVIDIA GPU (12-24 GB) and 64 GB RAM, exposing an OpenAI/Anthropic-compatible API on localhost.

Early signalLanguage modelsC+++0 stars today, ≈ 223 by evening
6.5
ollaya-dev/ollaya
A local runtime for decision models: pulls and serves classification and routing models behind a TypeSafe-compatible API. Like Ollama, but for models that return probabilities instead of text.

Early signalLanguage modelsRust+0 stars today, ≈ 166 by evening
6.3
deepfates/imp
A port of DSPy to the BEAM: declarative LM programs in Elixir with signatures, optimizers and agents running as OTP processes.

Early signalLanguage modelsElixir+0 stars today, ≈ 102 by evening
4.7
Mapika/decider
A language model that does not generate text: from a single forward pass it returns calibrated probabilities for typed questions (Choice, Score, Noul) about a given state. An open reproduction of the "System One" model…

BreakoutLanguage modelsPython+0 stars today, ≈ 231 by evening
4.6
NVIDIA/Model-Optimizer
NVIDIA library for compressing and accelerating models: quantization, pruning, distillation, NAS and speculative decoding with export to TensorRT-LLM, vLLM, SGLang. For ML engineers preparing models for deployment.

BreakoutLanguage modelsPython+0 stars today, ≈ 95 by evening
4.2
InternLM/Intern-Decision
A multimodal decision model built on Qwen3.5 that turns a state, optional images, and typed questions (choice, score, yes/no) into decisions with probabilities. Ships with training, two inference backends, temperature…

Early signalLanguage modelsPython+0 stars today, ≈ 33 by evening